fix(agent-office): alive를 heartbeat staleness로 판정 + 다운/복구 전이 발송실패 시 재시도 (최종 리뷰 I1·I2)

I1: collect_status - heartbeat 키 존재 여부가 아닌 ts age 기반으로 alive 판정.
    age > NODE_STALE_THRESHOLD_SEC(90s, env 주입 가능)이면 키 있어도 dead.
    config.py에 NODE_STALE_THRESHOLD_SEC=90 추가.
I2: check_and_alert - 다운/복구 전이 시 send_raw 실패하면 _node_state 갱신 보류.
    다음 사이클에서 동일 전이 재감지 → 재발송 시도 (다운 이벤트 유실 방지).
테스트: _hb 헬퍼 현재 시각 기본값으로 수정 + 신규 2개 (stale→dead, I2 재시도 회귀).
14 passed.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019LV86jBozkNhSFXJA412fq

agent-office/app/node_monitor.py

@@ -2,7 +2,7 @@
 from __future__ import annotations
 import datetime as dt, json, logging
 import redis.asyncio as aioredis
-from .config import REDIS_URL, NODE_ALERT_DEADLETTER_THRESHOLD
+from .config import REDIS_URL, NODE_ALERT_DEADLETTER_THRESHOLD, NODE_STALE_THRESHOLD_SEC
 
 logger = logging.getLogger("agent-office.node_monitor")
 
@@ -66,10 +66,13 @@ async def collect_status(redis=None) -> dict:
             if raw:
                 try:
                     hb = json.loads(raw)
-                    info.update(alive=True, state=hb.get("state"),
-                                jobs_done=hb.get("jobs_done", 0), jobs_failed=hb.get("jobs_failed", 0),
-                                last_job_at=hb.get("last_job_at"),
-                                last_beat_age_s=_beat_age(hb.get("ts") or "", now))
+                    age = _beat_age(hb.get("ts") or "", now)
+                    info["last_beat_age_s"] = age
+                    info["alive"] = age is not None and age <= NODE_STALE_THRESHOLD_SEC
+                    info["state"] = hb.get("state")
+                    info["jobs_done"] = hb.get("jobs_done", 0)
+                    info["jobs_failed"] = hb.get("jobs_failed", 0)
+                    info["last_job_at"] = hb.get("last_job_at")
                     if w["kind"] == "watcher" and hb.get("mode"):
                         out["paused_reason"] = hb["mode"]
                 except (json.JSONDecodeError, UnicodeDecodeError):
@@ -114,19 +117,24 @@ async def check_and_alert(status=None) -> list[str]:
         return []
     sent: list[str] = []
     for w in st["workers"]:
-        name, alive = w["name"], w.get("alive", False)
+        name = w["name"]
+        alive = w.get("alive", False)
         prev = _node_state.get(name)
+        transition_send_failed = False
         if prev is True and not alive:
             text = f"🔴 [{name}] 워커 다운"
             if (await send_raw(text=text)).get("ok"):
-                add_log("node_monitor", f"{name} 다운", "warning")
-                sent.append(text)
+                add_log("node_monitor", f"{name} 다운", "warning"); sent.append(text)
+            else:
+                transition_send_failed = True
         elif prev is False and alive:
             text = f"🟢 [{name}] 워커 복구"
             if (await send_raw(text=text)).get("ok"):
-                add_log("node_monitor", f"{name} 복구", "info")
-                sent.append(text)
-        _node_state[name] = alive
+                add_log("node_monitor", f"{name} 복구", "info"); sent.append(text)
+            else:
+                transition_send_failed = True
+        if not transition_send_failed:
+            _node_state[name] = alive
         dl = w.get("dead_letter", 0)
         if dl >= NODE_ALERT_DEADLETTER_THRESHOLD and dl != _dl_notified.get(name, 0):
             text = f"❌ [{name}] 실패 누적 {dl}건 (dead-letter)"